Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2654 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3509. Min Range: -5.3509
Max Act: 5.3509. Min Act: -0.1700
Data Index: 8443 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3509. Min Range: -5.3509
Max Act: 5.1009. Min Act: -0.1700
Data Index: 1809051 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3509. Min Range: -5.3509
Max Act: 5.0696. Min Act: -0.1700
Data Index: 4830109 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3509. Min Range: -5.3509
Max Act: 5.0384. Min Act: -0.1700
Data Index: 6681948 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.9759. Min Act: -0.1700
Data Index: 6625691 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.9759. Min Act: -0.1700
Data Index: 1090643 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.9446. Min Act: -0.1700
Data Index: 3861010 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.8821. Min Act: -0.1700
Data Index: 4089259 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.8196. Min Act: -0.1700
Data Index: 3472999 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.8509. Min Act: -0.1700
Data Index: 1482693 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.8509. Min Act: -0.1700
Data Index: 2011092 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.8509. Min Act: -0.1700
Data Index: 4897524 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.8196. Min Act: -0.1700
Data Index: 7980765 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.7884. Min Act: -0.1700
Data Index: 7031047 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.7571. Min Act: -0.1700
Data Index: 4046411 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.7571. Min Act: -0.1700
Data Index: 5673667 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.7571. Min Act: -0.1700
Data Index: 717299 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.7259. Min Act: -0.1700
Data Index: 2996275 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.6946. Min Act: -0.1700
Data Index: 1935639 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3509. Min Range: -5.3509
Max Act: 4.7259. Min Act: -0.1700
Data Index: 8435101 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19